Running Parallel Agents With Different Models in Cursor Mobile

Melvin Vivas · X post · 2026-07-19 · Open on X

Topics: AI Dev Tools & Productivity, AI Agents, Tool Use & MCP · Level: beginner

Summary

The creator starts several coding agents from the Cursor mobile app, each on a different model (Fable 5, GPT 5.6 Sol and Grok 4.5). The idea is to send the same work to several models at once and compare the results, even from a phone.

Key points

• Cursor mobile can start background/cloud agents away from your desk
• You can pick a different model for each agent
• Running the same task on several models lets you compare their output
• Models used: Fable 5, GPT 5.6 Sol, Grok 4.5

Resources mentioned

• Cursor · tool · x.com · free · recommended by both Bashiri Smith & Melvin Vivas
  AI-native code editor (VS Code with AI built in).
  Also in: GLM 5.3 and GLM 5.3 Flash now in Cursor (Melvin Vivas on X · notes), Grok Bot Can Now Hand Off Coding Tasks to Cursor (Melvin Vivas on X · notes), Why Plan Mode Still Matters in AI Coding Assistants (Codex, Claude, Cursor) (Melvin Vivas on X · notes), Why Plan Mode Still Matters in AI Coding Agents (Codex, Claude, Cursor) (Melvin Vivas on X · notes) and 121 more
• GPT 5.6 Sol · tool · openai.com · paid
  A GPT-family model available through an API, whose API and credit pricing was cut by over 20% for three months.
  Also in: Creator's Top 3 Closed Models: Fable 5, GPT 5.6 Sol, Grok 4.6 (Melvin Vivas on X · notes), Coworker v0.3.1: Telegram Streaming Sync, Built Fast with Codex (Melvin Vivas on X · notes), Coworker: Open-Source Grok Bot Clone Built on Pi and CopilotKit (Melvin Vivas on X · notes), GPT 5.6 Sol (medium) in ChatGPT for planning tasks (Melvin Vivas on X · notes) and 12 more
• Grok 4.5 · tool · x.ai · paid
  An LLM said to be trained in partnership with SpaceXAI, pitched as a general model beyond software engineering.
  Also in: Grok 4.5 Works Well as the Model Behind Hermes Agent (Melvin Vivas on X · notes), Models That Work With the Hermes Agent for Personal Productivity (Melvin Vivas on X · notes), Agent-Made Video in 10 Minutes: Hermes Agent + Grok 4.5 + Hyperframes (Melvin Vivas on X · notes), Personal Assistant Agent on Hermes: Morning Briefings and Inbox Triage (Melvin Vivas on X · notes) and 9 more
• Fable 5 · tool · anthropic.com · paid
  A frontier model used as the comparison point in the Claude Opus 5 announcement; the post gives no other details about it.
  Also in: Claude Opus 5.5 in Devin: #1 on FrontierCode 1.1 (Melvin Vivas on X · notes), Creator's Top 3 Closed Models: Fable 5, GPT 5.6 Sol, Grok 4.6 (Melvin Vivas on X · notes), Opus 5 vs Fable 5: Cost per Task in Cursor Benchmarks (Melvin Vivas on X · notes), Opus 5 Beats Fable 5 on Cost per Task and Tokens (Melvin Vivas on X · notes) and 7 more

Try this

• Try running one task with agents on several different models and compare the results